915 dependents
| Package | Description | Downloads/month |
|---|---|---|
| Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native... | 346.9M | |
| 🤗 Transformers: the model-definition framework for state-of-the-art machine lear... | 141.8M | |
| Python Library for Accessing the Cohere API | 38.3M | |
| Search infrastructure for AI | 13.7M | |
| Fast, Accurate, Lightweight Python library to make State of the Art Embedding | 11.6M | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 9.4M | |
| Faster Whisper transcription with CTranslate2 | 7.4M | |
| Framework for orchestrating role-playing, autonomous AI agents. By fostering col... | 7.4M | |
| 2.4M | ||
| The agent engineering platform | 1.6M | |
| The agent engineering platform | 1.1M | |
| Turn any computer or edge device into a command center for your computer vision ... | 1.1M | |
| aider is AI pair programming in your terminal | 864K | |
| Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, A... | 664K | |
| 🤖 A PyTorch library of curated Transformer models and their composable component... | 521K | |
| Fast State-of-the-Art Static Embeddings | 491K | |
| Deep Learning for humans | 467K | |
| PyTorch native post-training library | 405K | |
| On-device AI across mobile, embedded and edge for PyTorch | 238K | |
| Python Client for the Aleph Alpha API | 215K | |
| A high-throughput and memory-efficient inference and serving engine for LLMs | 143K | |
| AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup du... | 122K | |
| Turn any computer or edge device into a command center for your computer vision ... | 119K | |
| 80K | ||
| An autonomous agent that conducts deep research on any data using any LLM provid... | 74K | |
| Transformers for Information Retrieval, Text Classification, NER, QA, Language M... | 73K | |
| A convenient and user-friendly anime-style image data processing library that in... | 68K | |
| Modeling, training, eval, and inference code for OLMo | 55K | |
| Semantic memory layer for AI applications. REST API + MCP transport + knowledge ... | 54K | |
| A PyTorch native platform for training generative AI models | 54K | |
| An immersion toolkit for learning Languages through games and other visual media... | 50K | |
| Add diacritics to Hebrew text along with phonetic marks | 48K | |
| Sovereign AI companion - cognitive architecture, persistent memory, emotional mo... | 46K | |
| Data and tools for generating and inspecting OLMo pre-training data. | 44K | |
| MLX native implementations of state-of-the-art generative image models | 40K | |
| Things you can do with the token embeddings of an LLM | 38K | |
| AutoCoder: AutoCoder | 37K | |
| Easy-to-use and powerful LLM and SLM library with awesome model zoo. | 36K | |
| vMLX - Home of JANG_Q - Cont Batch, Prefix, Paged, KV Cache Quant, VL - Powers M... | 36K | |
| Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax | 34K | |
| Deep Learning for humans | 34K | |
| IAToolkit | 34K | |
| The official Python library for the anthropic-bedrock API | 33K | |
| An integration package connecting Upstage and LangChain | 33K | |
| Wheels & Docker images for running vLLM on CPU-only systems, optimized for diffe... | 31K | |
| GeoAI: Artificial Intelligence for Geospatial Data | 23K | |
| Tools for merging pretrained large language models. | 23K | |
| Go ahead and axolotl questions | 20K | |
| A nearly-live implementation of OpenAI's Whisper. | 20K | |
| Python SDK to configure and run evaluations for your LLM-based application | 19K |
